diff options
Diffstat (limited to 'fs')
55 files changed, 684 insertions, 326 deletions
diff --git a/fs/9p/conv.c b/fs/9p/conv.c index 32a9f99154e..bf1f1006796 100644 --- a/fs/9p/conv.c +++ b/fs/9p/conv.c @@ -116,13 +116,19 @@ static void buf_put_int64(struct cbuf *buf, u64 val) } } -static void buf_put_stringn(struct cbuf *buf, const char *s, u16 slen) +static char *buf_put_stringn(struct cbuf *buf, const char *s, u16 slen) { + char *ret; + + ret = NULL; if (buf_check_size(buf, slen + 2)) { buf_put_int16(buf, slen); + ret = buf->p; memcpy(buf->p, s, slen); buf->p += slen; } + + return ret; } static inline void buf_put_string(struct cbuf *buf, const char *s) @@ -430,15 +436,19 @@ static inline void v9fs_put_int64(struct cbuf *bufp, u64 val, u64 * p) static void v9fs_put_str(struct cbuf *bufp, char *data, struct v9fs_str *str) { - if (data) { - str->len = strlen(data); - str->str = bufp->p; - } else { - str->len = 0; - str->str = NULL; - } + int len; + char *s; + + if (data) + len = strlen(data); + else + len = 0; - buf_put_stringn(bufp, data, str->len); + s = buf_put_stringn(bufp, data, len); + if (str) { + str->len = len; + str->str = s; + } } static int diff --git a/fs/9p/mux.c b/fs/9p/mux.c index 945cb368d45..ea1134eb47c 100644 --- a/fs/9p/mux.c +++ b/fs/9p/mux.c @@ -471,10 +471,13 @@ static void v9fs_write_work(void *a) } spin_lock(&m->lock); - req = - list_entry(m->unsent_req_list.next, struct v9fs_req, +again: + req = list_entry(m->unsent_req_list.next, struct v9fs_req, req_list); list_move_tail(&req->req_list, &m->req_list); + if (req->err == ERREQFLUSH) + goto again; + m->wbuf = req->tcall->sdata; m->wsize = req->tcall->size; m->wpos = 0; @@ -525,7 +528,7 @@ static void process_request(struct v9fs_mux_data *m, struct v9fs_req *req) struct v9fs_str *ename; tag = req->tag; - if (req->rcall->id == RERROR && !req->err) { + if (!req->err && req->rcall->id == RERROR) { ecode = req->rcall->params.rerror.errno; ename = &req->rcall->params.rerror.error; @@ -551,7 +554,10 @@ static void process_request(struct v9fs_mux_data *m, struct v9fs_req *req) req->err = -EIO; } - if (req->cb && req->err != ERREQFLUSH) { + if (req->err == ERREQFLUSH) + return; + + if (req->cb) { dprintk(DEBUG_MUX, "calling callback tcall %p rcall %p\n", req->tcall, req->rcall); @@ -812,6 +818,7 @@ v9fs_mux_rpc_cb(void *a, struct v9fs_fcall *tc, struct v9fs_fcall *rc, int err) struct v9fs_mux_rpc *r; if (err == ERREQFLUSH) { + kfree(rc); dprintk(DEBUG_MUX, "err req flush\n"); return; } diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 91f552454c7..63e5b0398e8 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -886,8 +886,8 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen) } /* copy extension buffer into buffer */ - if (fcall->params.rstat.stat.extension.len < buflen) - buflen = fcall->params.rstat.stat.extension.len; + if (fcall->params.rstat.stat.extension.len+1 < buflen) + buflen = fcall->params.rstat.stat.extension.len + 1; memcpy(buffer, fcall->params.rstat.stat.extension.str, buflen - 1); buffer[buflen-1] = 0; @@ -951,7 +951,7 @@ static void *v9fs_vfs_follow_link(struct dentry *dentry, struct nameidata *nd) if (!link) link = ERR_PTR(-ENOMEM); else { - len = v9fs_readlink(dentry, link, strlen(link)); + len = v9fs_readlink(dentry, link, PATH_MAX); if (len < 0) { __putname(link); diff --git a/fs/Kconfig b/fs/Kconfig index 93b5dc4082f..e9749b0eecd 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -883,8 +883,6 @@ config CONFIGFS_FS Both sysfs and configfs can and should exist together on the same system. One is not a replacement for the other. - If unsure, say N. - endmenu menu "Miscellaneous filesystems" diff --git a/fs/buffer.c b/fs/buffer.c index 5e4a90ee103..62cfd17dc5f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2867,22 +2867,22 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) else if (test_set_buffer_locked(bh)) continue; - get_bh(bh); if (rw == WRITE || rw == SWRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; + get_bh(bh); submit_bh(WRITE, bh); continue; } } else { if (!buffer_uptodate(bh)) { bh->b_end_io = end_buffer_read_sync; + get_bh(bh); submit_bh(rw, bh); continue; } } unlock_buffer(bh); - put_bh(bh); } } diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index 8899d9c5f6b..f70e46951b3 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -36,6 +36,7 @@ struct configfs_dirent { int s_type; umode_t s_mode; struct dentry * s_dentry; + struct iattr * s_iattr; }; #define CONFIGFS_ROOT 0x0001 @@ -48,10 +49,11 @@ struct configfs_dirent { #define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR) extern struct vfsmount * configfs_mount; +extern kmem_cache_t *configfs_dir_cachep; extern int configfs_is_root(struct config_item *item); -extern struct inode * configfs_new_inode(mode_t mode); +extern struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent *); extern int configfs_create(struct dentry *, int mode, int (*init)(struct inode *)); extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); @@ -63,6 +65,7 @@ extern void configfs_hash_and_remove(struct dentry * dir, const char * name); extern const unsigned char * configfs_get_name(struct configfs_dirent *sd); extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent); +extern int configfs_setattr(struct dentry *dentry, struct iattr *iattr); extern int configfs_pin_fs(void); extern void configfs_release_fs(void); @@ -120,8 +123,10 @@ static inline struct config_item *configfs_get_config_item(struct dentry *dentry static inline void release_configfs_dirent(struct configfs_dirent * sd) { - if (!(sd->s_type & CONFIGFS_ROOT)) - kfree(sd); + if (!(sd->s_type & CONFIGFS_ROOT)) { + kfree(sd->s_iattr); + kmem_cache_free(configfs_dir_cachep, sd); + } } static inline struct configfs_dirent * configfs_get(struct configfs_dirent * sd) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index b668ec61527..ca60e3abef4 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -72,7 +72,7 @@ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent * pare { struct configfs_dirent * sd; - sd = kmalloc(sizeof(*sd), GFP_KERNEL); + sd = kmem_cache_alloc(configfs_dir_cachep, GFP_KERNEL); if (!sd) return NULL; @@ -136,13 +136,19 @@ static int create_dir(struct config_item * k, struct dentry * p, int error; umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; - error = configfs_create(d, mode, init_dir); + error = configfs_make_dirent(p->d_fsdata, d, k, mode, + CONFIGFS_DIR); if (!error) { - error = configfs_make_dirent(p->d_fsdata, d, k, mode, - CONFIGFS_DIR); + error = configfs_create(d, mode, init_dir); if (!error) { p->d_inode->i_nlink++; (d)->d_op = &configfs_dentry_ops; + } else { + struct configfs_dirent *sd = d->d_fsdata; + if (sd) { + list_del_init(&sd->s_sibling); + configfs_put(sd); + } } } return error; @@ -182,12 +188,19 @@ int configfs_create_link(struct configfs_symlink *sl, int err = 0; umode_t mode = S_IFLNK | S_IRWXUGO; - err = configfs_create(dentry, mode, init_symlink); + err = configfs_make_dirent(parent->d_fsdata, dentry, sl, mode, + CONFIGFS_ITEM_LINK); if (!err) { - err = configfs_make_dirent(parent->d_fsdata, dentry, sl, - mode, CONFIGFS_ITEM_LINK); + err = configfs_create(dentry, mode, init_symlink); if (!err) dentry->d_op = &configfs_dentry_ops; + else { + struct configfs_dirent *sd = dentry->d_fsdata; + if (sd) { + list_del_init(&sd->s_sibling); + configfs_put(sd); + } + } } return err; } @@ -241,13 +254,15 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den struct configfs_attribute * attr = sd->s_element; int error; + dentry->d_fsdata = configfs_get(sd); + sd->s_dentry = dentry; error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG, init_file); - if (error) + if (error) { + configfs_put(sd); return error; + } dentry->d_op = &configfs_dentry_ops; - dentry->d_fsdata = configfs_get(sd); - sd->s_dentry = dentry; d_rehash(dentry); return 0; @@ -839,6 +854,7 @@ struct inode_operations configfs_dir_inode_operations = { .symlink = configfs_symlink, .unlink = configfs_unlink, .lookup = configfs_lookup, + .setattr = configfs_setattr, }; #if 0 diff --git a/fs/configfs/file.c b/fs/configfs/file.c index c26cd61f13a..3921920d871 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -26,7 +26,6 @@ #include <linux/fs.h> #include <linux/module.h> -#include <linux/dnotify.h> #include <linux/slab.h> #include <asm/uaccess.h> #include <asm/semaphore.h> @@ -150,7 +149,7 @@ out: /** * fill_write_buffer - copy buffer from userspace. * @buffer: data buffer for file. - * @userbuf: data from user. + * @buf: data from user. * @count: number of bytes in @userbuf. * * Allocate @buffer->page if it hasn't been already, then @@ -177,8 +176,9 @@ fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size /** * flush_write_buffer - push buffer to config_item. - * @file: file pointer. + * @dentry: dentry to the attribute * @buffer: data buffer for file. + * @count: number of bytes * * Get the correct pointers for the config_item and the attribute we're * dealing with, then call the store() method for the attribute, @@ -217,15 +217,16 @@ static ssize_t configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct configfs_buffer * buffer = file->private_data; + ssize_t len; down(&buffer->sem); - count = fill_write_buffer(buffer,buf,count); - if (count > 0) - count = flush_write_buffer(file->f_dentry,buffer,count); - if (count > 0) - *ppos += count; + len = fill_write_buffer(buffer, buf, count); + if (len > 0) + len = flush_write_buffer(file->f_dentry, buffer, count); + if (len > 0) + *ppos += len; up(&buffer->sem); - return count; + return len; } static int check_perm(struct inode * inode, struct file * file) diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 6577c588de9..c153bd9534c 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -31,6 +31,7 @@ #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/backing-dev.h> +#include <linux/capability.h> #include <linux/configfs.h> #include "configfs_internal.h" @@ -48,18 +49,107 @@ static struct backing_dev_info configfs_backing_dev_info = { .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK, }; -struct inode * configfs_new_inode(mode_t mode) +static struct inode_operations configfs_inode_operations ={ + .setattr = configfs_setattr, +}; + +int configfs_setattr(struct dentry * dentry, struct iattr * iattr) +{ + struct inode * inode = dentry->d_inode; + struct configfs_dirent * sd = dentry->d_fsdata; + struct iattr * sd_iattr; + unsigned int ia_valid = iattr->ia_valid; + int error; + + if (!sd) + return -EINVAL; + + sd_iattr = sd->s_iattr; + + error = inode_change_ok(inode, iattr); + if (error) + return error; + + error = inode_setattr(inode, iattr); + if (error) + return error; + + if (!sd_iattr) { + /* setting attributes for the first time, allocate now */ + sd_iattr = kmalloc(sizeof(struct iattr), GFP_KERNEL); + if (!sd_iattr) + return -ENOMEM; + /* assign default attributes */ + memset(sd_iattr, 0, sizeof(struct iattr)); + sd_iattr->ia_mode = sd->s_mode; + sd_iattr->ia_uid = 0; + sd_iattr->ia_gid = 0; + sd_iattr->ia_atime = sd_iattr->ia_mtime = sd_iattr->ia_ctime = CURRENT_TIME; + sd->s_iattr = sd_iattr; + } + + /* attributes were changed atleast once in past */ + + if (ia_valid & ATTR_UID) + sd_iattr->ia_uid = iattr->ia_uid; + if (ia_valid & ATTR_GID) + sd_iattr->ia_gid = iattr->ia_gid; + if (ia_valid & ATTR_ATIME) + sd_iattr->ia_atime = timespec_trunc(iattr->ia_atime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_MTIME) + sd_iattr->ia_mtime = timespec_trunc(iattr->ia_mtime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_CTIME) + sd_iattr->ia_ctime = timespec_trunc(iattr->ia_ctime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_MODE) { + umode_t mode = iattr->ia_mode; + + if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + mode &= ~S_ISGID; + sd_iattr->ia_mode = sd->s_mode = mode; + } + + return error; +} + +static inline void set_default_inode_attr(struct inode * inode, mode_t mode) +{ + inode->i_mode = mode; + inode->i_uid = 0; + inode->i_gid = 0; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; +} + +static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) +{ + inode->i_mode = iattr->ia_mode; + inode->i_uid = iattr->ia_uid; + inode->i_gid = iattr->ia_gid; + inode->i_atime = iattr->ia_atime; + inode->i_mtime = iattr->ia_mtime; + inode->i_ctime = iattr->ia_ctime; +} + +struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd) { struct inode * inode = new_inode(configfs_sb); if (inode) { - inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; - inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->a_ops = &configfs_aops; inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; + inode->i_op = &configfs_inode_operations; + + if (sd->s_iattr) { + /* sysfs_dirent has non-default attributes + * get them for the new inode from persistent copy + * in sysfs_dirent + */ + set_inode_attr(inode, sd->s_iattr); + } else + set_default_inode_attr(inode, mode); } return inode; } @@ -70,7 +160,8 @@ int configfs_create(struct dentry * dentry, int mode, int (*init)(struct inode * struct inode * inode = NULL; if (dentry) { if (!dentry->d_inode) { - if ((inode = configfs_new_inode(mode))) { + struct configfs_dirent *sd = dentry->d_fsdata; + if ((inode = configfs_new_inode(mode, sd))) { if (dentry->d_parent && dentry->d_parent->d_inode) { struct inode *p_inode = dentry->d_parent->d_inode; p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME; @@ -103,10 +194,9 @@ int configfs_create(struct dentry * dentry, int mode, int (*init)(struct inode * */ const unsigned char * configfs_get_name(struct configfs_dirent *sd) { - struct attribute * attr; + struct configfs_attribute *attr; - if (!sd || !sd->s_element) - BUG(); + BUG_ON(!sd || !sd->s_element); /* These always have a dentry, so use that */ if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK)) @@ -114,7 +204,7 @@ const unsigned char * configfs_get_name(struct configfs_dirent *sd) if (sd->s_type & CONFIGFS_ITEM_ATTR) { attr = sd->s_element; - return attr->name; + return attr->ca_name; } return NULL; } @@ -130,13 +220,17 @@ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent) if (dentry) { spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); if (!(d_unhashed(dentry) && dentry->d_inode)) { dget_locked(dentry); __d_drop(dentry); + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); simple_unlink(parent->d_inode, dentry); - } else + } else { + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); + } } } @@ -145,6 +239,10 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name) struct configfs_dirent * sd; struct configfs_dirent * parent_sd = dir->d_fsdata; + if (dir->d_inode == NULL) + /* no inode means this hasn't been made visible yet */ + return; + mutex_lock(&dir->d_inode->i_mutex); list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { if (!sd->s_element) diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 1a2f6f6a4d9..f920d30478e 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -38,6 +38,7 @@ struct vfsmount * configfs_mount = NULL; struct super_block * configfs_sb = NULL; +kmem_cache_t *configfs_dir_cachep; static int configfs_mnt_count = 0; static struct super_operations configfs_ops = { @@ -62,6 +63,7 @@ static struct configfs_dirent configfs_root = { .s_children = LIST_HEAD_INIT(configfs_root.s_children), .s_element = &configfs_root_group.cg_item, .s_type = CONFIGFS_ROOT, + .s_iattr = NULL, }; static int configfs_fill_super(struct super_block *sb, void *data, int silent) @@ -73,9 +75,11 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = CONFIGFS_MAGIC; sb->s_op = &configfs_ops; + sb->s_time_gran = 1; configfs_sb = sb; - inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO); + inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, + &configfs_root); if (inode) { inode->i_op = &configfs_dir_inode_operations; inode->i_fop = &configfs_dir_operations; @@ -128,19 +132,31 @@ static decl_subsys(config, NULL, NULL); static int __init configfs_init(void) { - int err; + int err = -ENOMEM; + + configfs_dir_cachep = kmem_cache_create("configfs_dir_cache", + sizeof(struct configfs_dirent), + 0, 0, NULL, NULL); + if (!configfs_dir_cachep) + goto out; kset_set_kset_s(&config_subsys, kernel_subsys); err = subsystem_register(&config_subsys); - if (err) - return err; + if (err) { + kmem_cache_destroy(configfs_dir_cachep); + configfs_dir_cachep = NULL; + goto out; + } err = register_filesystem(&configfs_fs_type); if (err) { printk(KERN_ERR "configfs: Unable to register filesystem!\n"); subsystem_unregister(&config_subsys); + kmem_cache_destroy(configfs_dir_cachep); + configfs_dir_cachep = NULL; } +out: return err; } @@ -148,11 +164,13 @@ static void __exit configfs_exit(void) { unregister_filesystem(&configfs_fs_type); subsystem_unregister(&config_subsys); + kmem_cache_destroy(configfs_dir_cachep); + configfs_dir_cachep = NULL; } MODULE_AUTHOR("Oracle"); MODULE_LICENSE("GPL"); -MODULE_VERSION("0.0.1"); +MODULE_VERSION("0.0.2"); MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration."); module_init(configfs_init); diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 50f5840521a..e5512e295cf 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -162,8 +162,7 @@ int configfs_unlink(struct inode *dir, struct dentry *dentry) if (!(sd->s_type & CONFIGFS_ITEM_LINK)) goto out; - if (dentry->d_parent == configfs_sb->s_root) - BUG(); + BUG_ON(dentry->d_parent == configfs_sb->s_root); sl = sd->s_element; @@ -277,5 +276,6 @@ struct inode_operations configfs_symlink_inode_operations = { .follow_link = configfs_follow_link, .readlink = generic_readlink, .put_link = configfs_put_link, + .setattr = configfs_setattr, }; diff --git a/fs/dcache.c b/fs/dcache.c index 86bdb93789c..a173bba3266 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -743,7 +743,9 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) dentry->d_op = NULL; dentry->d_fsdata = NULL; dentry->d_mounted = 0; +#ifdef CONFIG_PROFILING dentry->d_cookie = NULL; +#endif INIT_HLIST_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); diff --git a/fs/direct-io.c b/fs/direct-io.c index 30dbbd1df51..848044af7e1 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -857,6 +857,7 @@ do_holes: /* Handle holes */ if (!buffer_mapped(map_bh)) { char *kaddr; + loff_t i_size_aligned; /* AKPM: eargh, -ENOTBLK is a hack */ if (dio->rw == WRITE) { @@ -864,8 +865,14 @@ do_holes: return -ENOTBLK; } + /* + * Be sure to account for a partial block as the + * last block in the file + */ + i_size_aligned = ALIGN(i_size_read(dio->inode), + 1 << blkbits); if (dio->block_in_file >= - i_size_read(dio->inode)>>blkbits) { + i_size_aligned >> blkbits) { /* We hit eof */ page_cache_release(page); goto out; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 35acc43b897..da52b4a5db6 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -220,7 +220,7 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl) struct ext2_inode_info *ei = EXT2_I(inode); int name_index; void *value = NULL; - size_t size; + size_t size = 0; int error; if (S_ISLNK(inode->i_mode)) diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 74714af4ae6..e52765219e1 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -605,7 +605,7 @@ got: insert_inode_hash(inode); if (DQUOT_ALLOC_INODE(inode)) { - err = -ENOSPC; + err = -EDQUOT; goto fail_drop; } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 8d6819846fc..cb6f9bd658d 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -221,6 +221,11 @@ static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",grpquota"); #endif +#if defined(CONFIG_EXT2_FS_XIP) + if (sbi->s_mount_opt & EXT2_MOUNT_XIP) + seq_puts(seq, ",xip"); +#endif + return 0; } diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 47a9da2dfb4..0d21d558b87 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -226,7 +226,7 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type, struct ext3_inode_info *ei = EXT3_I(inode); int name_index; void *value = NULL; - size_t size; + size_t size = 0; int error; if (S_ISLNK(inode->i_mode)) diff --git a/fs/fat/file.c b/fs/fat/file.c index e99c5a73b39..88aa1ae13f9 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -210,10 +210,30 @@ static int fat_free(struct inode *inode, int skip) if (MSDOS_I(inode)->i_start == 0) return 0; - /* - * Write a new EOF, and get the remaining cluster chain for freeing. - */ + fat_cache_inval_inode(inode); + wait = IS_DIRSYNC(inode); + i_start = free_start = MSDOS_I(inode)->i_start; + i_logstart = MSDOS_I(inode)->i_logstart; + + /* First, we write the new file size. */ + if (!skip) { + MSDOS_I(inode)->i_start = 0; + MSDOS_I(inode)->i_logstart = 0; + } + MSDOS_I(inode)->i_attrs |= ATTR_ARCH; + inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; + if (wait) { + err = fat_sync_inode(inode); + if (err) { + MSDOS_I(inode)->i_start = i_start; + MSDOS_I(inode)->i_logstart = i_logstart; + return err; + } + } else + mark_inode_dirty(inode); + + /* Write a new EOF, and get the remaining cluster chain for freeing. */ if (skip) { struct fat_entry fatent; int ret, fclus, dclus; @@ -244,35 +264,11 @@ static int fat_free(struct inode *inode, int skip) return ret; free_start = ret; - i_start = i_logstart = 0; - fat_cache_inval_inode(inode); - } else { - fat_cache_inval_inode(inode); - - i_start = free_start = MSDOS_I(inode)->i_start; - i_logstart = MSDOS_I(inode)->i_logstart; - MSDOS_I(inode)->i_start = 0; - MSDOS_I(inode)->i_logstart = 0; } - MSDOS_I(inode)->i_attrs |= ATTR_ARCH; - inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; - if (wait) { - err = fat_sync_inode(inode); - if (err) - goto error; - } else - mark_inode_dirty(inode); inode->i_blocks = skip << (MSDOS_SB(sb)->cluster_bits - 9); /* Freeing the remained cluster chain */ return fat_free_clusters(inode, free_start); - -error: - if (i_start) { - MSDOS_I(inode)->i_start = i_start; - MSDOS_I(inode)->i_logstart = i_logstart; - } - return err; } void fat_truncate(struct inode *inode) diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 32fb0a3f1da..944652e9dde 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -196,19 +196,9 @@ EXPORT_SYMBOL_GPL(fat_date_unix2dos); int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs) { - int i, e, err = 0; + int i, err = 0; - for (i = 0; i < nr_bhs; i++) { - lock_buffer(bhs[i]); - if (test_clear_buffer_dirty(bhs[i])) { - get_bh(bhs[i]); - bhs[i]->b_end_io = end_buffer_write_sync; - e = submit_bh(WRITE, bhs[i]); - if (!err && e) - err = e; - } else - unlock_buffer(bhs[i]); - } + ll_rw_block(SWRITE, nr_bhs, bhs); for (i = 0; i < nr_bhs; i++) { wait_on_buffer(bhs[i]); if (buffer_eopnotsupp(bhs[i])) { diff --git a/fs/fcntl.c b/fs/fcntl.c index 5f96786d1c7..dc4a7007f4e 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -208,8 +208,11 @@ static int setfl(int fd, struct file * filp, unsigned long arg) struct inode * inode = filp->f_dentry->d_inode; int error = 0; - /* O_APPEND cannot be cleared if the file is marked as append-only */ - if (!(arg & O_APPEND) && IS_APPEND(inode)) + /* + * O_APPEND cannot be cleared if the file is marked as append-only + * and the file is open for write. + */ + if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ diff --git a/fs/file.c b/fs/file.c index fd066b261c7..cea7cbea11d 100644 --- a/fs/file.c +++ b/fs/file.c @@ -379,7 +379,6 @@ static void __devinit fdtable_defer_list_init(int cpu) void __init files_defer_init(void) { int i; - /* Really early - can't use for_each_cpu */ - for (i = 0; i < NR_CPUS; i++) + for_each_cpu(i) fdtable_defer_list_init(i); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4526da8907c..f556a0d5c0d 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -120,9 +120,9 @@ struct fuse_req *fuse_get_request(struct fuse_conn *fc) return do_get_request(fc); } +/* Must be called with fuse_lock held */ static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req) { - spin_lock(&fuse_lock); if (req->preallocated) { atomic_dec(&fc->num_waiting); list_add(&req->list, &fc->unused_list); @@ -134,11 +134,19 @@ static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req) fc->outstanding_debt--; else up(&fc->outstanding_sem); - spin_unlock(&fuse_lock); } void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req) { + if (atomic_dec_and_test(&req->count)) { + spin_lock(&fuse_lock); + fuse_putback_request(fc, req); + spin_unlock(&fuse_lock); + } +} + +static void fuse_put_request_locked(struct fuse_conn *fc, struct fuse_req *req) +{ if (atomic_dec_and_test(&req->count)) fuse_putback_request(fc, req); } @@ -163,26 +171,36 @@ void fuse_release_background(struct fuse_req *req) * still waiting), the 'end' callback is called if given, else the * reference to the request is released * + * Releasing extra reference for foreground requests must be done + * within the same locked region as setting state to finished. This + * is because fuse_reset_request() may be called after request is + * finished and it must be the sole possessor. If request is + * interrupted and put in the background, it will return with an error + * and hence never be reset and reused. + * * Called with fuse_lock, unlocks it */ static void request_end(struct fuse_conn *fc, struct fuse_req *req) { - void (*end) (struct fuse_conn *, struct fuse_req *) = req->end; - req->end = NULL; list_del(&req->list); req->state = FUSE_REQ_FINISHED; - spin_unlock(&fuse_lock); - if (req->background) { + if (!req->background) { + wake_up(&req->waitq); + fuse_put_request_locked(fc, req); + spin_unlock(&fuse_lock); + } else { + void (*end) (struct fuse_conn *, struct fuse_req *) = req->end; + req->end = NULL; + spin_unlock(&fuse_lock); down_read(&fc->sbput_sem); if (fc->mounted) fuse_release_background(req); up_read(&fc->sbput_sem); + if (end) + end(fc, req); + else + fuse_put_request(fc, req); } - wake_up(&req->waitq); - if (end) - end(fc, req); - else - fuse_put_request(fc, req); } /* diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 429f4b263cf..ca917973c2c 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -1308,6 +1308,7 @@ int journal_stop(handle_t *handle) transaction_t *transaction = handle->h_transaction; journal_t *journal = transaction->t_journal; int old_handle_count, err; + pid_t pid; J_ASSERT(transaction->t_updates > 0); J_ASSERT(journal_current_handle() == handle); @@ -1333,8 +1334,15 @@ int journal_stop(handle_t *handle) * It doesn't cost much - we're about to run a commit and sleep * on IO anyway. Speeds up many-threaded, many-dir operations * by 30x or more... + * + * But don't do this if this process was the most recent one to + * perform a synchronous write. We do this to detect the case where a + * single process is doing a stream of sync writes. No point in waiting + * for joiners in that case. */ - if (handle->h_sync) { + pid = current->pid; + if (handle->h_sync && journal->j_last_sync_writer != pid) { + journal->j_last_sync_writer = pid; do { old_handle_count = transaction->t_handle_count; schedule_timeout_uninterruptible(1); diff --git a/fs/jffs/intrep.c b/fs/jffs/intrep.c index b2e95421d93..ce7b54b0b2b 100644 --- a/fs/jffs/intrep.c +++ b/fs/jffs/intrep.c @@ -1965,7 +1965,7 @@ retry: iovec_cnt++; if (JFFS_GET_PAD_BYTES(raw_inode->nsize)) { - static char allff[3]={255,255,255}; + static unsigned char allff[3]={255,255,255}; /* Add some extra padding if necessary */ node_iovec[iovec_cnt].iov_base = allff; node_iovec[iovec_cnt].iov_len = diff --git a/fs/libfs.c b/fs/libfs.c index 63c020e6589..71fd08fa410 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -388,6 +388,7 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; + inode->i_nlink = 2; root = d_alloc_root(inode); if (!root) { iput(inode); diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 14552403957..220058d8616 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -22,12 +22,14 @@ #define NLMDBG_FACILITY NLMDBG_CLIENT #define NLMCLNT_GRACE_WAIT (5*HZ) #define NLMCLNT_POLL_TIMEOUT (30*HZ) +#define NLMCLNT_MAX_RETRIES 3 static int nlmclnt_test(struct nlm_rqst *, struct file_lock *); static int nlmclnt_lock(struct nlm_rqst *, struct file_lock *); static int nlmclnt_unlock(struct nlm_rqst *, struct file_lock *); static int nlm_stat_to_errno(u32 stat); static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *host); +static int nlmclnt_cancel(struct nlm_host *, int , struct file_lock *); static const struct rpc_call_ops nlmclnt_unlock_ops; static const struct rpc_call_ops nlmclnt_cancel_ops; @@ -598,7 +600,7 @@ out_unblock: nlmclnt_finish_block(req); /* Cancel the blocked request if it is still pending */ if (resp->status == NLM_LCK_BLOCKED) - nlmclnt_cancel(host, fl); + nlmclnt_cancel(host, req->a_args.block, fl); out: nlmclnt_release_lockargs(req); return status; @@ -728,8 +730,7 @@ static const struct rpc_call_ops nlmclnt_unlock_ops = { * We always use an async RPC call for this in order not to hang a * process that has been Ctrl-C'ed. */ -int -nlmclnt_cancel(struct nlm_host *host, struct file_lock *fl) +static int nlmclnt_cancel(struct nlm_host *host, int block, struct file_lock *fl) { struct nlm_rqst *req; unsigned long flags; @@ -750,6 +751,7 @@ nlmclnt_cancel(struct nlm_host *host, struct file_lock *fl) req->a_flags = RPC_TASK_ASYNC; nlmclnt_setlockargs(req, fl); + req->a_args.block = block; status = nlmclnt_async_call(req, NLMPROC_CANCEL, &nlmclnt_cancel_ops); if (status < 0) { @@ -801,6 +803,9 @@ die: return; retry_cancel: + /* Don't ever retry more than 3 times */ + if (req->a_retries++ >= NLMCLNT_MAX_RETRIES) + goto die; nlm_rebind_host(req->a_host); rpc_restart_call(task); rpc_delay(task, 30 * HZ); diff --git a/fs/namei.c b/fs/namei.c index 7ac9fb4acb2..faf61c35308 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -790,7 +790,7 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) inode = nd->dentry->d_inode; if (nd->depth) - lookup_flags = LOOKUP_FOLLOW; + lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE); /* At this point we know we have a real path component. */ for(;;) { @@ -885,7 +885,8 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) last_with_slashes: lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; last_component: - nd->flags &= ~LOOKUP_CONTINUE; + /* Clear LOOKUP_CONTINUE iff it was previously unset */ + nd->flags &= lookup_flags | ~LOOKUP_CONTINUE; if (lookup_flags & LOOKUP_PARENT) goto lookup_parent; if (this.name[0] == '.') switch (this.len) { @@ -1069,6 +1070,8 @@ static int fastcall do_path_lookup(int dfd, const char *name, unsigned int flags, struct nameidata *nd) { int retval = 0; + int fput_needed; + struct file *file; nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags; @@ -1090,29 +1093,22 @@ static int fastcall do_path_lookup(int dfd, const char *name, nd->mnt = mntget(current->fs->pwdmnt); nd->dentry = dget(current->fs->pwd); } else { - struct file *file; - int fput_needed; struct dentry *dentry; file = fget_light(dfd, &fput_needed); - if (!file) { - retval = -EBADF; - goto out_fail; - } + retval = -EBADF; + if (!file) + goto unlock_fail; dentry = file->f_dentry; - if (!S_ISDIR(dentry->d_inode->i_mode)) { - retval = -ENOTDIR; - fput_light(file, fput_needed); - goto out_fail; - } + retval = -ENOTDIR; + if (!S_ISDIR(dentry->d_inode->i_mode)) + goto fput_unlock_fail; retval = file_permission(file, MAY_EXEC); - if (retval) { - fput_light(file, fput_needed); - goto out_fail; - } + if (retval) + goto fput_unlock_fail; nd->mnt = mntget(file->f_vfsmnt); nd->dentry = dget(dentry); @@ -1126,7 +1122,12 @@ out: if (unlikely(current->audit_context && nd && nd->dentry && nd->dentry->d_inode)) audit_inode(name, nd->dentry->d_inode, flags); -out_fail: + return retval; + +fput_unlock_fail: + fput_light(file, fput_needed); +unlock_fail: + read_unlock(¤t->fs->lock); return retval; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 10ae377e68f..04ab2fc360e 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -481,7 +481,7 @@ retry: if (wdata->verf.committed != NFS_FILE_SYNC) { need_commit = 1; if (memcmp(&first_verf.verifier, &wdata->verf.verifier, - sizeof(first_verf.verifier))); + sizeof(first_verf.verifier))) goto sync_retry; } diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index d424041b38e..bae3d7548be 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -58,7 +58,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, goto out; } - down(&OCFS2_I(inode)->ip_io_sem); + mutex_lock(&OCFS2_I(inode)->ip_io_mutex); lock_buffer(bh); set_buffer_uptodate(bh); @@ -82,7 +82,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, brelse(bh); } - up(&OCFS2_I(inode)->ip_io_sem); + mutex_unlock(&OCFS2_I(inode)->ip_io_mutex); out: mlog_exit(ret); return ret; @@ -125,13 +125,13 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr, flags &= ~OCFS2_BH_CACHED; if (inode) - down(&OCFS2_I(inode)->ip_io_sem); + mutex_lock(&OCFS2_I(inode)->ip_io_mutex); for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { bhs[i] = sb_getblk(sb, block++); if (bhs[i] == NULL) { if (inode) - up(&OCFS2_I(inode)->ip_io_sem); + mutex_unlock(&OCFS2_I(inode)->ip_io_mutex); status = -EIO; mlog_errno(status); goto bail; @@ -220,7 +220,7 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr, ocfs2_set_buffer_uptodate(inode, bh); } if (inode) - up(&OCFS2_I(inode)->ip_io_sem); + mutex_unlock(&OCFS2_I(inode)->ip_io_mutex); mlog(ML_BH_IO, "block=(%"MLFu64"), nr=(%d), cached=%s\n", block, nr, (!(flags & OCFS2_BH_CACHED) || ignore_cache) ? "no" : "yes"); diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 7307ba52891..d08971d29b6 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -917,8 +917,9 @@ static int o2hb_thread(void *data) elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb); mlog(0, "start = %lu.%lu, end = %lu.%lu, msec = %u\n", - before_hb.tv_sec, before_hb.tv_usec, - after_hb.tv_sec, after_hb.tv_usec, elapsed_msec); + before_hb.tv_sec, (unsigned long) before_hb.tv_usec, + after_hb.tv_sec, (unsigned long) after_hb.tv_usec, + elapsed_msec); if (elapsed_msec < reg->hr_timeout_ms) { /* the kthread api has blocked signals for us so no diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 35d92c01a97..d22d4cf08db 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1285,14 +1285,16 @@ static void o2net_idle_timer(unsigned long data) mlog(ML_NOTICE, "here are some times that might help debug the " "situation: (tmr %ld.%ld now %ld.%ld dr %ld.%ld adv " "%ld.%ld:%ld.%ld func (%08x:%u) %ld.%ld:%ld.%ld)\n", - sc->sc_tv_timer.tv_sec, sc->sc_tv_timer.tv_usec, - now.tv_sec, now.tv_usec, - sc->sc_tv_data_ready.tv_sec, sc->sc_tv_data_ready.tv_usec, - sc->sc_tv_advance_start.tv_sec, sc->sc_tv_advance_start.tv_usec, - sc->sc_tv_advance_stop.tv_sec, sc->sc_tv_advance_stop.tv_usec, + sc->sc_tv_timer.tv_sec, (long) sc->sc_tv_timer.tv_usec, + now.tv_sec, (long) now.tv_usec, + sc->sc_tv_data_ready.tv_sec, (long) sc->sc_tv_data_ready.tv_usec, + sc->sc_tv_advance_start.tv_sec, + (long) sc->sc_tv_advance_start.tv_usec, + sc->sc_tv_advance_stop.tv_sec, + (long) sc->sc_tv_advance_stop.tv_usec, sc->sc_msg_key, sc->sc_msg_type, - sc->sc_tv_func_start.tv_sec, sc->sc_tv_func_start.tv_usec, - sc->sc_tv_func_stop.tv_sec, sc->sc_tv_func_stop.tv_usec); + sc->sc_tv_func_start.tv_sec, (long) sc->sc_tv_func_start.tv_usec, + sc->sc_tv_func_stop.tv_sec, (long) sc->sc_tv_func_stop.tv_usec); o2net_sc_queue_work(sc, &sc->sc_shutdown_work); } diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index 3fecba0a602..42eb53b5293 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -657,6 +657,7 @@ void dlm_complete_thread(struct dlm_ctxt *dlm); int dlm_launch_recovery_thread(struct dlm_ctxt *dlm); void dlm_complete_recovery_thread(struct dlm_ctxt *dlm); void dlm_wait_for_recovery(struct dlm_ctxt *dlm); +int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node); void dlm_put(struct dlm_ctxt *dlm); struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm); diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index da3c22045f8..6ee30837389 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -573,8 +573,11 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data) spin_lock(&dlm_domain_lock); dlm = __dlm_lookup_domain_full(query->domain, query->name_len); /* Once the dlm ctxt is marked as leaving then we don't want - * to be put in someone's domain map. */ + * to be put in someone's domain map. + * Also, explicitly disallow joining at certain troublesome + * times (ie. during recovery). */ if (dlm && dlm->dlm_state != DLM_CTXT_LEAVING) { + int bit = query->node_idx; spin_lock(&dlm->spinlock); if (dlm->dlm_state == DLM_CTXT_NEW && @@ -586,6 +589,19 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data) } else if (dlm->joining_node != DLM_LOCK_RES_OWNER_UNKNOWN) { /* Disallow parallel joins. */ response = JOIN_DISALLOW; + } else if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) { + mlog(ML_NOTICE, "node %u trying to join, but recovery " + "is ongoing.\n", bit); + response = JOIN_DISALLOW; + } else if (test_bit(bit, dlm->recovery_map)) { + mlog(ML_NOTICE, "node %u trying to join, but it " + "still needs recovery.\n", bit); + response = JOIN_DISALLOW; + } else if (test_bit(bit, dlm->domain_map)) { + mlog(ML_NOTICE, "node %u trying to join, but it " + "is still in the domain! needs recovery?\n", + bit); + response = JOIN_DISALLOW; } else { /* Alright we're fully a part of this domain * so we keep some state as to who's joining diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 27e984f7e4c..a3194fe173d 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1050,17 +1050,10 @@ static int dlm_restart_lock_mastery(struct dlm_ctxt *dlm, node = dlm_bitmap_diff_iter_next(&bdi, &sc); while (node >= 0) { if (sc == NODE_UP) { - /* a node came up. easy. might not even need - * to talk to it if its node number is higher - * or if we are already blocked. */ - mlog(0, "node up! %d\n", node); - if (blocked) - goto next; - - if (node > dlm->node_num) { - mlog(0, "node > this node. skipping.\n"); - goto next; - } + /* a node came up. clear any old vote from + * the response map and set it in the vote map + * then restart the mastery. */ + mlog(ML_NOTICE, "node %d up while restarting\n", node); /* redo the master request, but only for the new node */ mlog(0, "sending request to new node\n"); @@ -2005,6 +1998,15 @@ fail: break; mlog(0, "timed out during migration\n"); + /* avoid hang during shutdown when migrating lockres + * to a node which also goes down */ + if (dlm_is_node_dead(dlm, target)) { + mlog(0, "%s:%.*s: expected migration target %u " + "is no longer up. restarting.\n", + dlm->name, res->lockname.len, + res->lockname.name, target); + ret = -ERESTARTSYS; + } } if (ret == -ERESTARTSYS) { /* migration failed, detach and clean up mle */ diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 0c8eb1093f0..186e9a76aa5 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -39,6 +39,7 @@ #include <linux/inet.h> #include <linux/timer.h> #include <linux/kthread.h> +#include <linux/delay.h> #include "cluster/heartbeat.h" @@ -256,6 +257,27 @@ static int dlm_recovery_thread(void *data) return 0; } +/* returns true when the recovery master has contacted us */ +static int dlm_reco_master_ready(struct dlm_ctxt *dlm) +{ + int ready; + spin_lock(&dlm->spinlock); + ready = (dlm->reco.new_master != O2NM_INVALID_NODE_NUM); + spin_unlock(&dlm->spinlock); + return ready; +} + +/* returns true if node is no longer in the domain + * could be dead or just not joined */ +int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node) +{ + int dead; + spin_lock(&dlm->spinlock); + dead = test_bit(node, dlm->domain_map); + spin_unlock(&dlm->spinlock); + return dead; +} + /* callers of the top-level api calls (dlmlock/dlmunlock) should * block on the dlm->reco.event when recovery is in progress. * the dlm recovery thread will set this state when it begins @@ -297,6 +319,7 @@ static void dlm_end_recovery(struct dlm_ctxt *dlm) static int dlm_do_recovery(struct dlm_ctxt *dlm) { int status = 0; + int ret; spin_lock(&dlm->spinlock); @@ -343,10 +366,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) goto master_here; if (dlm->reco.new_master == O2NM_INVALID_NODE_NUM) { - /* choose a new master */ - if (!dlm_pick_recovery_master(dlm)) { + /* choose a new master, returns 0 if this node + * is the master, -EEXIST if it's another node. + * this does not return until a new master is chosen + * or recovery completes entirely. */ + ret = dlm_pick_recovery_master(dlm); + if (!ret) { /* already notified everyone. go. */ - dlm->reco.new_master = dlm->node_num; goto master_here; } mlog(0, "another node will master this recovery session.\n"); @@ -371,8 +397,13 @@ master_here: if (status < 0) { mlog(ML_ERROR, "error %d remastering locks for node %u, " "retrying.\n", status, dlm->reco.dead_node); + /* yield a bit to allow any final network messages + * to get handled on remaining nodes */ + msleep(100); } else { /* success! see if any other nodes need recovery */ + mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n", + dlm->name, dlm->reco.dead_node, dlm->node_num); dlm_reset_recovery(dlm); } dlm_end_recovery(dlm); @@ -477,7 +508,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) BUG(); break; case DLM_RECO_NODE_DATA_DEAD: - mlog(0, "node %u died after " + mlog(ML_NOTICE, "node %u died after " "requesting recovery info for " "node %u\n", ndata->node_num, dead_node); @@ -485,6 +516,19 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) // start all over destroy = 1; status = -EAGAIN; + /* instead of spinning like crazy here, + * wait for the domain map to catch up + * with the network state. otherwise this + * can be hit hundreds of times before + * the node is really seen as dead. */ + wait_event_timeout(dlm->dlm_reco_thread_wq, + dlm_is_node_dead(dlm, + ndata->node_num), + msecs_to_jiffies(1000)); + mlog(0, "waited 1 sec for %u, " + "dead? %s\n", ndata->node_num, + dlm_is_node_dead(dlm, ndata->node_num) ? + "yes" : "no"); goto leave; case DLM_RECO_NODE_DATA_RECEIVING: case DLM_RECO_NODE_DATA_REQUESTED: @@ -678,11 +722,27 @@ static void dlm_request_all_locks_worker(struct dlm_work_item *item, void *data) dlm = item->dlm; dead_node = item->u.ral.dead_node; reco_master = item->u.ral.reco_master; + mres = (struct dlm_migratable_lockres *)data; + + if (dead_node != dlm->reco.dead_node || + reco_master != dlm->reco.new_master) { + /* show extra debug info if the recovery state is messed */ + mlog(ML_ERROR, "%s: bad reco state: reco(dead=%u, master=%u), " + "request(dead=%u, master=%u)\n", + dlm->name, dlm->reco.dead_node, dlm->reco.new_master, + dead_node, reco_master); + mlog(ML_ERROR, "%s: name=%.*s master=%u locks=%u/%u flags=%u " + "entry[0]={c=%"MLFu64",l=%u,f=%u,t=%d,ct=%d,hb=%d,n=%u}\n", + dlm->name, mres->lockname_len, mres->lockname, mres->master, + mres->num_locks, mres->total_locks, mres->flags, + mres->ml[0].cookie, mres->ml[0].list, mres->ml[0].flags, + mres->ml[0].type, mres->ml[0].convert_type, + mres->ml[0].highest_blocked, mres->ml[0].node); + BUG(); + } BUG_ON(dead_node != dlm->reco.dead_node); BUG_ON(reco_master != dlm->reco.new_master); - mres = (struct dlm_migratable_lockres *)data; - /* lock resources should have already been moved to the * dlm->reco.resources list. now move items from that list * to a temp list if the dead owner matches. note that the @@ -757,15 +817,18 @@ int dlm_reco_data_done_handler(struct o2net_msg *msg, u32 len, void *data) continue; switch (ndata->state) { + /* should have moved beyond INIT but not to FINALIZE yet */ case DLM_RECO_NODE_DATA_INIT: case DLM_RECO_NODE_DATA_DEAD: - case DLM_RECO_NODE_DATA_DONE: case DLM_RECO_NODE_DATA_FINALIZE_SENT: mlog(ML_ERROR, "bad ndata state for node %u:" " state=%d\n", ndata->node_num, ndata->state); BUG(); break; + /* these states are possible at this point, anywhere along + * the line of recovery */ + case DLM_RECO_NODE_DATA_DONE: case DLM_RECO_NODE_DATA_RECEIVING: case DLM_RECO_NODE_DATA_REQUESTED: case DLM_RECO_NODE_DATA_REQUESTING: @@ -799,13 +862,31 @@ static void dlm_move_reco_locks_to_list(struct dlm_ctxt *dlm, { struct dlm_lock_resource *res; struct list_head *iter, *iter2; + struct dlm_lock *lock; spin_lock(&dlm->spinlock); list_for_each_safe(iter, iter2, &dlm->reco.resources) { res = list_entry (iter, struct dlm_lock_resource, recovering); + /* always prune any $RECOVERY entries for dead nodes, + * otherwise hangs can occur during later recovery */ if (dlm_is_recovery_lock(res->lockname.name, - res->lockname.len)) + res->lockname.len)) { + spin_lock(&res->spinlock); + list_for_each_entry(lock, &res->granted, list) { + if (lock->ml.node == dead_node) { + mlog(0, "AHA! there was " + "a $RECOVERY lock for dead " + "node %u (%s)!\n", + dead_node, dlm->name); + list_del_init(&lock->list); + dlm_lock_put(lock); + break; + } + } + spin_unlock(&res->spinlock); continue; + } + if (res->owner == dead_node) { mlog(0, "found lockres owned by dead node while " "doing recovery for node %u. sending it.\n", @@ -1179,7 +1260,7 @@ static void dlm_mig_lockres_worker(struct dlm_work_item *item, void *data) again: ret = dlm_lockres_master_requery(dlm, res, &real_master); if (ret < 0) { - mlog(0, "dlm_lockres_master_requery failure: %d\n", + mlog(0, "dlm_lockres_master_requery ret=%d\n", ret); goto again; } @@ -1757,6 +1838,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) struct dlm_lock_resource *res; int i; struct list_head *bucket; + struct dlm_lock *lock; /* purge any stale mles */ @@ -1780,10 +1862,25 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) bucket = &(dlm->resources[i]); list_for_each(iter, bucket) { res = list_entry (iter, struct dlm_lock_resource, list); + /* always prune any $RECOVERY entries for dead nodes, + * otherwise hangs can occur during later recovery */ if (dlm_is_recovery_lock(res->lockname.name, - res->lockname.len)) + res->lockname.len)) { + spin_lock(&res->spinlock); + list_for_each_entry(lock, &res->granted, list) { + if (lock->ml.node == dead_node) { + mlog(0, "AHA! there was " + "a $RECOVERY lock for dead " + "node %u (%s)!\n", + dead_node, dlm->name); + list_del_init(&lock->list); + dlm_lock_put(lock); + break; + } + } + spin_unlock(&res->spinlock); continue; - + } spin_lock(&res->spinlock); /* zero the lvb if necessary */ dlm_revalidate_lvb(dlm, res, dead_node); @@ -1869,12 +1966,9 @@ void dlm_hb_node_up_cb(struct o2nm_node *node, int idx, void *data) return; spin_lock(&dlm->spinlock); - set_bit(idx, dlm->live_nodes_map); - - /* notify any mles attached to the heartbeat events */ - dlm_hb_event_notify_attached(dlm, idx, 1); - + /* do NOT notify mle attached to the heartbeat events. + * new nodes are not interesting in mastery until joined. */ spin_unlock(&dlm->spinlock); dlm_put(dlm); @@ -1897,7 +1991,18 @@ static void dlm_reco_unlock_ast(void *astdata, enum dlm_status st) mlog(0, "unlockast for recovery lock fired!\n"); } - +/* + * dlm_pick_recovery_master will continually attempt to use + * dlmlock() on the special "$RECOVERY" lockres with the + * LKM_NOQUEUE flag to get an EX. every thread that enters + * this function on each node racing to become the recovery + * master will not stop attempting this until either: + * a) this node gets the EX (and becomes the recovery master), + * or b) dlm->reco.new_master gets set to some nodenum + * != O2NM_INVALID_NODE_NUM (another node will do the reco). + * so each time a recovery master is needed, the entire cluster + * will sync at this point. if the new master dies, that will + * be detected in dlm_do_recovery */ static int dlm_pick_recovery_master(struct dlm_ctxt *dlm) { enum dlm_status ret; @@ -1906,23 +2011,45 @@ static int dlm_pick_recovery_master(struct dlm_ctxt *dlm) mlog(0, "starting recovery of %s at %lu, dead=%u, this=%u\n", dlm->name, jiffies, dlm->reco.dead_node, dlm->node_num); -retry: +again: memset(&lksb, 0, sizeof(lksb)); ret = dlmlock(dlm, LKM_EXMODE, &lksb, LKM_NOQUEUE|LKM_RECOVERY, DLM_RECOVERY_LOCK_NAME, dlm_reco_ast, dlm, dlm_reco_bast); + mlog(0, "%s: dlmlock($RECOVERY) returned %d, lksb=%d\n", + dlm->name, ret, lksb.status); + if (ret == DLM_NORMAL) { mlog(0, "dlm=%s dlmlock says I got it (this=%u)\n", dlm->name, dlm->node_num); - /* I am master, send message to all nodes saying - * that I am beginning a recovery session */ - status = dlm_send_begin_reco_message(dlm, - dlm->reco.dead_node); + + /* got the EX lock. check to see if another node + * just became the reco master */ + if (dlm_reco_master_ready(dlm)) { + mlog(0, "%s: got reco EX lock, but %u will " + "do the recovery\n", dlm->name, + dlm->reco.new_master); + status = -EEXIST; + } else { + status = dlm_send_begin_reco_message(dlm, + dlm->reco.dead_node); + /* this always succeeds */ + BUG_ON(status); + + /* set the new_master to this node */ + spin_lock(&dlm->spinlock); + dlm->reco.new_master = dlm->node_num; + spin_unlock(&dlm->spinlock); + } /* recovery lock is a special case. ast will not get fired, * so just go ahead and unlock it. */ ret = dlmunlock(dlm, &lksb, 0, dlm_reco_unlock_ast, dlm); + if (ret == DLM_DENIED) { + mlog(0, "got DLM_DENIED, trying LKM_CANCEL\n"); + ret = dlmunlock(dlm, &lksb, LKM_CANCEL, dlm_reco_unlock_ast, dlm); + } if (ret != DLM_NORMAL) { /* this would really suck. this could only happen * if there was a network error during the unlock @@ -1930,20 +2057,42 @@ retry: * is actually "done" and the lock structure is * even freed. we can continue, but only * because this specific lock name is special. */ - mlog(0, "dlmunlock returned %d\n", ret); - } - - if (status < 0) { - mlog(0, "failed to send recovery message. " - "must retry with new node map.\n"); - goto retry; + mlog(ML_ERROR, "dlmunlock returned %d\n", ret); } } else if (ret == DLM_NOTQUEUED) { mlog(0, "dlm=%s dlmlock says another node got it (this=%u)\n", dlm->name, dlm->node_num); /* another node is master. wait on - * reco.new_master != O2NM_INVALID_NODE_NUM */ + * reco.new_master != O2NM_INVALID_NODE_NUM + * for at most one second */ + wait_event_timeout(dlm->dlm_reco_thread_wq, + dlm_reco_master_ready(dlm), + msecs_to_jiffies(1000)); + if (!dlm_reco_master_ready(dlm)) { + mlog(0, "%s: reco master taking awhile\n", + dlm->name); + goto again; + } + /* another node has informed this one that it is reco master */ + mlog(0, "%s: reco master %u is ready to recover %u\n", + dlm->name, dlm->reco.new_master, dlm->reco.dead_node); status = -EEXIST; + } else { + struct dlm_lock_resource *res; + + /* dlmlock returned something other than NOTQUEUED or NORMAL */ + mlog(ML_ERROR, "%s: got %s from dlmlock($RECOVERY), " + "lksb.status=%s\n", dlm->name, dlm_errname(ret), + dlm_errname(lksb.status)); + res = dlm_lookup_lockres(dlm, DLM_RECOVERY_LOCK_NAME, + DLM_RECOVERY_LOCK_NAME_LEN); + if (res) { + dlm_print_one_lock_resource(res); + dlm_lockres_put(res); + } else { + mlog(ML_ERROR, "recovery lock not found\n"); + } + BUG(); } return status; @@ -1982,7 +2131,7 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node) mlog(0, "not sending begin reco to self\n"); continue; } - +retry: ret = -EINVAL; mlog(0, "attempting to send begin reco msg to %d\n", nodenum); @@ -1991,8 +2140,17 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node) /* negative status is handled ok by caller here */ if (ret >= 0) ret = status; + if (dlm_is_host_down(ret)) { + /* node is down. not involved in recovery + * so just keep going */ + mlog(0, "%s: node %u was down when sending " + "begin reco msg (%d)\n", dlm->name, nodenum, ret); + ret = 0; + } if (ret < 0) { struct dlm_lock_resource *res; + /* this is now a serious problem, possibly ENOMEM + * in the network stack. must retry */ mlog_errno(ret); mlog(ML_ERROR, "begin reco of dlm %s to node %u " " returned %d\n", dlm->name, nodenum, ret); @@ -2004,7 +2162,10 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node) } else { mlog(ML_ERROR, "recovery lock not found\n"); } - break; + /* sleep for a bit in hopes that we can avoid + * another ENOMEM */ + msleep(100); + goto retry; } } @@ -2027,19 +2188,34 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data) spin_lock(&dlm->spinlock); if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM) { - mlog(0, "new_master already set to %u!\n", - dlm->reco.new_master); + if (test_bit(dlm->reco.new_master, dlm->recovery_map)) { + mlog(0, "%s: new_master %u died, changing " + "to %u\n", dlm->name, dlm->reco.new_master, + br->node_idx); + } else { + mlog(0, "%s: new_master %u NOT DEAD, changing " + "to %u\n", dlm->name, dlm->reco.new_master, + br->node_idx); + /* may not have seen the new master as dead yet */ + } } if (dlm->reco.dead_node != O2NM_INVALID_NODE_NUM) { - mlog(0, "dead_node already set to %u!\n", - dlm->reco.dead_node); + mlog(ML_NOTICE, "%s: dead_node previously set to %u, " + "node %u changing it to %u\n", dlm->name, + dlm->reco.dead_node, br->node_idx, br->dead_node); } dlm->reco.new_master = br->node_idx; dlm->reco.dead_node = br->dead_node; if (!test_bit(br->dead_node, dlm->recovery_map)) { - mlog(ML_ERROR, "recovery master %u sees %u as dead, but this " + mlog(0, "recovery master %u sees %u as dead, but this " "node has not yet. marking %u as dead\n", br->node_idx, br->dead_node, br->dead_node); + if (!test_bit(br->dead_node, dlm->domain_map) || + !test_bit(br->dead_node, dlm->live_nodes_map)) + mlog(0, "%u not in domain/live_nodes map " + "so setting it in reco map manually\n", + br->dead_node); + set_bit(br->dead_node, dlm->recovery_map); __dlm_hb_node_down(dlm, br->dead_node); } spin_unlock(&dlm->spinlock); diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index cec2ce1cd31..c95f08d2e92 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -188,6 +188,19 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, actions &= ~(DLM_UNLOCK_REMOVE_LOCK| DLM_UNLOCK_REGRANT_LOCK| DLM_UNLOCK_CLEAR_CONVERT_TYPE); + } else if (status == DLM_RECOVERING || + status == DLM_MIGRATING || + status == DLM_FORWARD) { + /* must clear the actions because this unlock + * is about to be retried. cannot free or do + * any list manipulation. */ + mlog(0, "%s:%.*s: clearing actions, %s\n", + dlm->name, res->lockname.len, + res->lockname.name, + status==DLM_RECOVERING?"recovering": + (status==DLM_MIGRATING?"migrating": + "forward")); + actions = 0; } if (flags & LKM_CANCEL) lock->cancel_pending = 0; diff --git a/fs/ocfs2/dlm/userdlm.c b/fs/ocfs2/dlm/userdlm.c index e1fdd288796..c3764f4744e 100644 --- a/fs/ocfs2/dlm/userdlm.c +++ b/fs/ocfs2/dlm/userdlm.c @@ -27,7 +27,7 @@ * Boston, MA 021110-1307, USA. */ -#include <asm/signal.h> +#include <linux/signal.h> #include <linux/module.h> #include <linux/fs.h> diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index f2fb40cd296..b6ba292e954 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -262,8 +262,7 @@ static int ocfs2_extent_map_find_leaf(struct inode *inode, el = &eb->h_list; } - if (el->l_tree_depth) - BUG(); + BUG_ON(el->l_tree_depth); for (i = 0; i < le16_to_cpu(el->l_next_free_rec); i++) { rec = &el->l_recs[i]; @@ -364,8 +363,8 @@ static int ocfs2_extent_map_lookup_read(struct inode *inode, return ret; } - if (ent->e_tree_depth) - BUG(); /* FIXME: Make sure this isn't a corruption */ + /* FIXME: Make sure this isn't a corruption */ + BUG_ON(ent->e_tree_depth); *ret_ent = ent; @@ -423,8 +422,7 @@ static int ocfs2_extent_map_try_insert(struct inode *inode, le32_to_cpu(rec->e_clusters), NULL, NULL); - if (!old_ent) - BUG(); + BUG_ON(!old_ent); ret = -EEXIST; if (old_ent->e_tree_depth < tree_depth) @@ -988,7 +986,7 @@ int __init init_ocfs2_extent_maps(void) return 0; } -void __exit exit_ocfs2_extent_maps(void) +void exit_ocfs2_extent_maps(void) { kmem_cache_destroy(ocfs2_em_ent_cachep); } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index eaf33caa0a1..1715bc90e70 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1022,8 +1022,9 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, } newsize = count + saved_pos; - mlog(0, "pos=%lld newsize=%"MLFu64" cursize=%lld\n", - saved_pos, newsize, i_size_read(inode)); + mlog(0, "pos=%lld newsize=%lld cursize=%lld\n", + (long long) saved_pos, (long long) newsize, + (long long) i_size_read(inode)); /* No need for a higher level metadata lock if we're * never going past i_size. */ @@ -1042,8 +1043,9 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, spin_unlock(&OCFS2_I(inode)->ip_lock); mlog(0, "Writing at EOF, may need more allocation: " - "i_size = %lld, newsize = %"MLFu64", need %u clusters\n", - i_size_read(inode), newsize, clusters); + "i_size = %lld, newsize = %lld, need %u clusters\n", + (long long) i_size_read(inode), (long long) newsize, + clusters); /* We only want to continue the rest of this loop if * our extend will actually require more diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index d4ecc062771..8122489c576 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -903,10 +903,10 @@ void ocfs2_clear_inode(struct inode *inode) "Clear inode of %"MLFu64", inode is locked\n", oi->ip_blkno); - mlog_bug_on_msg(down_trylock(&oi->ip_io_sem), - "Clear inode of %"MLFu64", io_sem is locked\n", + mlog_bug_on_msg(!mutex_trylock(&oi->ip_io_mutex), + "Clear inode of %"MLFu64", io_mutex is locked\n", oi->ip_blkno); - up(&oi->ip_io_sem); + mutex_unlock(&oi->ip_io_mutex); /* * down_trylock() returns 0, down_write_trylock() returns 1 diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 9b017743365..84c50796128 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -46,10 +46,10 @@ struct ocfs2_inode_info struct list_head ip_io_markers; int ip_orphaned_slot; - struct semaphore ip_io_sem; + struct mutex ip_io_mutex; /* Used by the journalling code to attach an inode to a - * handle. These are protected by ip_io_sem in order to lock + * handle. These are protected by ip_io_mutex in order to lock * out other I/O to the inode until we either commit or * abort. */ struct list_head ip_handle_list; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 303c8d96457..fa0bcac5cea 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -147,8 +147,7 @@ struct ocfs2_journal_handle *ocfs2_start_trans(struct ocfs2_super *osb, mlog_entry("(max_buffs = %d)\n", max_buffs); - if (!osb || !osb->journal->j_journal) - BUG(); + BUG_ON(!osb || !osb->journal->j_journal); if (ocfs2_is_hard_readonly(osb)) { ret = -EROFS; @@ -401,7 +400,7 @@ int ocfs2_journal_access(struct ocfs2_journal_handle *handle, * j_trans_barrier for us. */ ocfs2_set_inode_lock_trans(OCFS2_SB(inode->i_sb)->journal, inode); - down(&OCFS2_I(inode)->ip_io_sem); + mutex_lock(&OCFS2_I(inode)->ip_io_mutex); switch (type) { case OCFS2_JOURNAL_ACCESS_CREATE: case OCFS2_JOURNAL_ACCESS_WRITE: @@ -416,7 +415,7 @@ int ocfs2_journal_access(struct ocfs2_journal_handle *handle, status = -EINVAL; mlog(ML_ERROR, "Uknown access type!\n"); } - up(&OCFS2_I(inode)->ip_io_sem); + mutex_unlock(&OCFS2_I(inode)->ip_io_mutex); if (status < 0) mlog(ML_ERROR, "Error %d getting %d access to buffer!\n", @@ -561,7 +560,11 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty) SET_INODE_JOURNAL(inode); OCFS2_I(inode)->ip_open_count++; - status = ocfs2_meta_lock(inode, NULL, &bh, 1); + /* Skip recovery waits here - journal inode metadata never + * changes in a live cluster so it can be considered an + * exception to the rule. */ + status = ocfs2_meta_lock_full(inode, NULL, &bh, 1, + OCFS2_META_LOCK_RECOVERY); if (status < 0) { if (status != -ERESTARTSYS) mlog(ML_ERROR, "Could not get lock on journal!\n"); @@ -672,8 +675,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb) mlog_entry_void(); - if (!osb) - BUG(); + BUG_ON(!osb); journal = osb->journal; if (!journal) @@ -805,8 +807,7 @@ int ocfs2_journal_wipe(struct ocfs2_journal *journal, int full) mlog_entry_void(); - if (!journal) - BUG(); + BUG_ON(!journal); status = journal_wipe(journal->j_journal, full); if (status < 0) { @@ -1072,10 +1073,10 @@ restart: NULL); bail: - down(&osb->recovery_lock); + mutex_lock(&osb->recovery_lock); if (!status && !ocfs2_node_map_is_empty(osb, &osb->recovery_map)) { - up(&osb->recovery_lock); + mutex_unlock(&osb->recovery_lock); goto restart; } @@ -1083,7 +1084,7 @@ bail: mb(); /* sync with ocfs2_recovery_thread_running */ wake_up(&osb->recovery_event); - up(&osb->recovery_lock); + mutex_unlock(&osb->recovery_lock); mlog_exit(status); /* no one is callint kthread_stop() for us so the kthread() api @@ -1098,7 +1099,7 @@ void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) mlog_entry("(node_num=%d, osb->node_num = %d)\n", node_num, osb->node_num); - down(&osb->recovery_lock); + mutex_lock(&osb->recovery_lock); if (osb->disable_recovery) goto out; @@ -1120,7 +1121,7 @@ void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) } out: - up(&osb->recovery_lock); + mutex_unlock(&osb->recovery_lock); wake_up(&osb->recovery_event); mlog_exit_void(); @@ -1271,8 +1272,7 @@ static int ocfs2_recover_node(struct ocfs2_super *osb, /* Should not ever be called to recover ourselves -- in that * case we should've called ocfs2_journal_load instead. */ - if (osb->node_num == node_num) - BUG(); + BUG_ON(osb->node_num == node_num); slot_num = ocfs2_node_num_to_slot(si, node_num); if (slot_num == OCFS2_INVALID_SLOT) { diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index f468c600cf9..8d8e4779df9 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -33,6 +33,7 @@ #include <linux/rbtree.h> #include <linux/workqueue.h> #include <linux/kref.h> +#include <linux/mutex.h> #include "cluster/nodemanager.h" #include "cluster/heartbeat.h" @@ -233,7 +234,7 @@ struct ocfs2_super struct proc_dir_entry *proc_sub_dir; /* points to /proc/fs/ocfs2/<maj_min> */ atomic_t vol_state; - struct semaphore recovery_lock; + struct mutex recovery_lock; struct task_struct *recovery_thread_task; int disable_recovery; wait_queue_head_t checkpoint_event; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 364d64bd5f1..046824b6b62 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -932,7 +932,7 @@ static void ocfs2_inode_init_once(void *data, oi->ip_dir_start_lookup = 0; init_rwsem(&oi->ip_alloc_sem); - init_MUTEX(&(oi->ip_io_sem)); + mutex_init(&oi->ip_io_mutex); oi->ip_blkno = 0ULL; oi->ip_clusters = 0; @@ -1137,9 +1137,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) /* disable any new recovery threads and wait for any currently * running ones to exit. Do this before setting the vol_state. */ - down(&osb->recovery_lock); + mutex_lock(&osb->recovery_lock); osb->disable_recovery = 1; - up(&osb->recovery_lock); + mutex_unlock(&osb->recovery_lock); wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb)); /* At this point, we know that no more recovery threads can be @@ -1254,8 +1254,7 @@ static int ocfs2_initialize_super(struct super_block *sb, osb->sb = sb; /* Save off for ocfs2_rw_direct */ osb->s_sectsize_bits = blksize_bits(sector_size); - if (!osb->s_sectsize_bits) - BUG(); + BUG_ON(!osb->s_sectsize_bits); osb->net_response_ids = 0; spin_lock_init(&osb->net_response_lock); @@ -1283,7 +1282,7 @@ static int ocfs2_initialize_super(struct super_block *sb, snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u", MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev)); - init_MUTEX(&osb->recovery_lock); + mutex_init(&osb->recovery_lock); osb->disable_recovery = 0; osb->recovery_thread_task = NULL; diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c index 600a8bc5b54..fc29cb7a437 100644 --- a/fs/ocfs2/sysfile.c +++ b/fs/ocfs2/sysfile.c @@ -77,8 +77,7 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb, if (arr && ((inode = *arr) != NULL)) { /* get a ref in addition to the array ref */ inode = igrab(inode); - if (!inode) - BUG(); + BUG_ON(!inode); return inode; } @@ -89,8 +88,7 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb, /* add one more if putting into array for first time */ if (arr && inode) { *arr = igrab(inode); - if (!*arr) - BUG(); + BUG_ON(!*arr); } return inode; } diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c index 3a0458fd3e1..300b5bedfb2 100644 --- a/fs/ocfs2/uptodate.c +++ b/fs/ocfs2/uptodate.c @@ -388,7 +388,7 @@ out_free: } } -/* Item insertion is guarded by ip_io_sem, so the insertion path takes +/* Item insertion is guarded by ip_io_mutex, so the insertion path takes * advantage of this by not rechecking for a duplicate insert during * the slow case. Additionally, if the cache needs to be bumped up to * a tree, the code will not recheck after acquiring the lock -- @@ -418,7 +418,7 @@ void ocfs2_set_buffer_uptodate(struct inode *inode, (unsigned long long) bh->b_blocknr); /* No need to recheck under spinlock - insertion is guarded by - * ip_io_sem */ + * ip_io_mutex */ spin_lock(&oi->ip_lock); if (ocfs2_insert_can_use_array(oi, ci)) { /* Fast case - it's an array and there's a free @@ -440,7 +440,7 @@ void ocfs2_set_buffer_uptodate(struct inode *inode, /* Called against a newly allocated buffer. Most likely nobody should * be able to read this sort of metadata while it's still being - * allocated, but this is careful to take ip_io_sem anyway. */ + * allocated, but this is careful to take ip_io_mutex anyway. */ void ocfs2_set_new_buffer_uptodate(struct inode *inode, struct buffer_head *bh) { @@ -451,9 +451,9 @@ void ocfs2_set_new_buffer_uptodate(struct inode *inode, set_buffer_uptodate(bh); - down(&oi->ip_io_sem); + mutex_lock(&oi->ip_io_mutex); ocfs2_set_buffer_uptodate(inode, bh); - up(&oi->ip_io_sem); + mutex_unlock(&oi->ip_io_mutex); } /* Requires ip_lock. */ @@ -537,7 +537,7 @@ int __init init_ocfs2_uptodate_cache(void) return 0; } -void __exit exit_ocfs2_uptodate_cache(void) +void exit_ocfs2_uptodate_cache(void) { if (ocfs2_uptodate_cachep) kmem_cache_destroy(ocfs2_uptodate_cachep); diff --git a/fs/ocfs2/uptodate.h b/fs/ocfs2/uptodate.h index e5aacdf4eab..01cd32d26b0 100644 --- a/fs/ocfs2/uptodate.h +++ b/fs/ocfs2/uptodate.h @@ -27,7 +27,7 @@ #define OCFS2_UPTODATE_H int __init init_ocfs2_uptodate_cache(void); -void __exit exit_ocfs2_uptodate_cache(void); +void exit_ocfs2_uptodate_cache(void); void ocfs2_metadata_cache_init(struct inode *inode); void ocfs2_metadata_cache_purge(struct inode *inode); diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 8f8014285a3..1d24fead51a 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -548,7 +548,7 @@ static int show_stat(struct seq_file *p, void *v) } seq_printf(p, "intr %llu", (unsigned long long)sum); -#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) +#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) && !defined(CONFIG_IA64) for (i = 0; i < NR_IRQS; i++) seq_printf(p, " %u", kstat_irqs(i)); #endif diff --git a/fs/quota_v2.c b/fs/quota_v2.c index a4ef91bb4f3..b4199ec3ece 100644 --- a/fs/quota_v2.c +++ b/fs/quota_v2.c @@ -35,7 +35,7 @@ static int v2_check_quota_file(struct super_block *sb, int type) size = sb->s_op->quota_read(sb, type, (char *)&dqhead, sizeof(struct v2_disk_dqheader), 0); if (size != sizeof(struct v2_disk_dqheader)) { - printk("quota_v2: failed read expected=%d got=%d\n", + printk("quota_v2: failed read expected=%zd got=%zd\n", sizeof(struct v2_disk_dqheader), size); return 0; } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 77891de0e02..ef5e5414e7a 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1125,7 +1125,7 @@ static void handle_attrs(struct super_block *s) REISERFS_SB(s)->s_mount_opt &= ~(1 << REISERFS_ATTRS); } } else if (le32_to_cpu(rs->s_flags) & reiserfs_attrs_cleared) { - REISERFS_SB(s)->s_mount_opt |= REISERFS_ATTRS; + REISERFS_SB(s)->s_mount_opt |= (1 << REISERFS_ATTRS); } } diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index 4fae57d9d11..201049ac8a9 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -579,10 +579,9 @@ static void udf_table_free_blocks(struct super_block * sb, { loffset = nextoffset; aed->lengthAllocDescs = cpu_to_le32(adsize); - if (obh) - sptr = UDF_I_DATA(inode) + nextoffset - udf_file_entry_alloc_offset(inode) + UDF_I_LENEATTR(inode) - adsize; - else - sptr = obh->b_data + nextoffset - adsize; + sptr = UDF_I_DATA(inode) + nextoffset - + udf_file_entry_alloc_offset(inode) + + UDF_I_LENEATTR(inode) - adsize; dptr = nbh->b_data + sizeof(struct allocExtDesc); memcpy(dptr, sptr, adsize); nextoffset = sizeof(struct allocExtDesc) + adsize; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index ca732e79c48..ab9a7629d23 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -296,7 +296,7 @@ static struct dentry * udf_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { struct inode *inode = NULL; - struct fileIdentDesc cfi, *fi; + struct fileIdentDesc cfi; struct udf_fileident_bh fibh; if (dentry->d_name.len > UDF_NAME_LEN-2) @@ -318,7 +318,7 @@ udf_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) else #endif /* UDF_RECOVERY */ - if ((fi = udf_find_entry(dir, dentry, &fibh, &cfi))) + if (udf_find_entry(dir, dentry, &fibh, &cfi)) { if (fibh.sbh != fibh.ebh) udf_release_data(fibh.ebh); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index e0c04e36a05..3c3f62ce2ad 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -376,7 +376,7 @@ out: * This function gets the block which contains the fragment. */ -static int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create) +int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create) { struct super_block * sb = inode->i_sb; struct ufs_sb_private_info * uspi = UFS_SB(sb)->s_uspi; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index d4aacee593f..e9055ef7f5a 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -388,7 +388,8 @@ static int ufs_parse_options (char * options, unsigned * mount_options) /* * Read on-disk structures associated with cylinder groups */ -static int ufs_read_cylinder_structures (struct super_block *sb) { +static int ufs_read_cylinder_structures (struct super_block *sb) +{ struct ufs_sb_info * sbi = UFS_SB(sb); struct ufs_sb_private_info * uspi; struct ufs_super_block *usb; @@ -415,6 +416,7 @@ static int ufs_read_cylinder_structures (struct super_block *sb) { base = space = kmalloc(size, GFP_KERNEL); if (!base) goto failed; + sbi->s_csp = (struct ufs_csum *)space; for (i = 0; i < blks; i += uspi->s_fpb) { size = uspi->s_bsize; if (i + uspi->s_fpb > blks) @@ -430,7 +432,6 @@ static int ufs_read_cylinder_structures (struct super_block *sb) { goto failed; ubh_ubhcpymem (space, ubh, size); - sbi->s_csp[ufs_fragstoblks(i)]=(struct ufs_csum *)space; space += size; ubh_brelse (ubh); @@ -486,7 +487,8 @@ failed: * Put on-disk structures associated with cylinder groups and * write them back to disk */ -static void ufs_put_cylinder_structures (struct super_block *sb) { +static void ufs_put_cylinder_structures (struct super_block *sb) +{ struct ufs_sb_info * sbi = UFS_SB(sb); struct ufs_sb_private_info * uspi; struct ufs_buffer_head * ubh; @@ -499,7 +501,7 @@ static void ufs_put_cylinder_structures (struct super_block *sb) { size = uspi->s_cssize; blks = (size + uspi->s_fsize - 1) >> uspi->s_fshift; - base = space = (char*) sbi->s_csp[0]; + base = space = (char*) sbi->s_csp; for (i = 0; i < blks; i += uspi->s_fpb) { size = uspi->s_bsize; if (i + uspi->s_fpb > blks) diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index 61d2e35012a..02e86291ef8 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -29,6 +29,11 @@ * Idea from Pierre del Perugia <delperug@gla.ecoledoc.ibp.fr> */ +/* + * Modified to avoid infinite loop on 2006 by + * Evgeniy Dushistov <dushistov@mail.ru> + */ + #include <linux/errno.h> #include <linux/fs.h> #include <linux/ufs_fs.h> @@ -65,19 +70,16 @@ #define DIRECT_BLOCK ((inode->i_size + uspi->s_bsize - 1) >> uspi->s_bshift) #define DIRECT_FRAGMENT ((inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift) -#define DATA_BUFFER_USED(bh) \ - (atomic_read(&bh->b_count)>1 || buffer_locked(bh)) static int ufs_trunc_direct (struct inode * inode) { struct ufs_inode_info *ufsi = UFS_I(inode); struct super_block * sb; struct ufs_sb_private_info * uspi; - struct buffer_head * bh; __fs32 * p; unsigned frag1, frag2, frag3, frag4, block1, block2; unsigned frag_to_free, free_count; - unsigned i, j, tmp; + unsigned i, tmp; int retry; UFSD(("ENTER\n")) @@ -117,15 +119,7 @@ static int ufs_trunc_direct (struct inode * inode) ufs_panic (sb, "ufs_trunc_direct", "internal error"); frag1 = ufs_fragnum (frag1); frag2 = ufs_fragnum (frag2); - for (j = frag1; j < frag2; j++) { - bh = sb_find_get_block (sb, tmp + j); - if ((bh && DATA_BUFFER_USED(bh)) || tmp != fs32_to_cpu(sb, *p)) { - retry = 1; - brelse (bh); - goto next1; - } - bforget (bh); - } + inode->i_blocks -= (frag2-frag1) << uspi->s_nspfshift; mark_inode_dirty(inode); ufs_free_fragments (inode, tmp + frag1, frag2 - frag1); @@ -140,15 +134,7 @@ next1: tmp = fs32_to_cpu(sb, *p); if (!tmp) continue; - for (j = 0; j < uspi->s_fpb; j++) { - bh = sb_find_get_block(sb, tmp + j); - if ((bh && DATA_BUFFER_USED(bh)) || tmp != fs32_to_cpu(sb, *p)) { - retry = 1; - brelse (bh); - goto next2; - } - bforget (bh); - } + *p = 0; inode->i_blocks -= uspi->s_nspb; mark_inode_dirty(inode); @@ -162,7 +148,6 @@ next1: frag_to_free = tmp; free_count = uspi->s_fpb; } -next2:; } if (free_count > 0) @@ -179,15 +164,7 @@ next2:; if (!tmp ) ufs_panic(sb, "ufs_truncate_direct", "internal error"); frag4 = ufs_fragnum (frag4); - for (j = 0; j < frag4; j++) { - bh = sb_find_get_block (sb, tmp + j); - if ((bh && DATA_BUFFER_USED(bh)) || tmp != fs32_to_cpu(sb, *p)) { - retry = 1; - brelse (bh); - goto next1; - } - bforget (bh); - } + *p = 0; inode->i_blocks -= frag4 << uspi->s_nspfshift; mark_inode_dirty(inode); @@ -204,9 +181,8 @@ static int ufs_trunc_indirect (struct inode * inode, unsigned offset, __fs32 *p) struct super_block * sb; struct ufs_sb_private_info * uspi; struct ufs_buffer_head * ind_ubh; - struct buffer_head * bh; __fs32 * ind; - unsigned indirect_block, i, j, tmp; + unsigned indirect_block, i, tmp; unsigned frag_to_free, free_count; int retry; @@ -238,15 +214,7 @@ static int ufs_trunc_indirect (struct inode * inode, unsigned offset, __fs32 *p) tmp = fs32_to_cpu(sb, *ind); if (!tmp) continue; - for (j = 0; j < uspi->s_fpb; j++) { - bh = sb_find_get_block(sb, tmp + j); - if ((bh && DATA_BUFFER_USED(bh)) || tmp != fs32_to_cpu(sb, *ind)) { - retry = 1; - brelse (bh); - goto next; - } - bforget (bh); - } + *ind = 0; ubh_mark_buffer_dirty(ind_ubh); if (free_count == 0) { @@ -261,7 +229,6 @@ static int ufs_trunc_indirect (struct inode * inode, unsigned offset, __fs32 *p) } inode->i_blocks -= uspi->s_nspb; mark_inode_dirty(inode); -next:; } if (free_count > 0) { @@ -430,9 +397,7 @@ void ufs_truncate (struct inode * inode) struct ufs_inode_info *ufsi = UFS_I(inode); struct super_block * sb; struct ufs_sb_private_info * uspi; - struct buffer_head * bh; - unsigned offset; - int err, retry; + int retry; UFSD(("ENTER\n")) sb = inode->i_sb; @@ -442,6 +407,9 @@ void ufs_truncate (struct inode * inode) return; if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return; + + block_truncate_page(inode->i_mapping, inode->i_size, ufs_getfrag_block); + lock_kernel(); while (1) { retry = ufs_trunc_direct(inode); @@ -457,15 +425,7 @@ void ufs_truncate (struct inode * inode) blk_run_address_space(inode->i_mapping); yield(); } - offset = inode->i_size & uspi->s_fshift; - if (offset) { - bh = ufs_bread (inode, inode->i_size >> uspi->s_fshift, 0, &err); - if (bh) { - memset (bh->b_data + offset, 0, uspi->s_fsize - offset); - mark_buffer_dirty (bh); - brelse (bh); - } - } + inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; ufsi->i_lastfrag = DIRECT_FRAGMENT; unlock_kernel(); |